Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rafael-adcp/kraken/plugin install krakenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/rafael-adcp/kraken/stop-failure)<a href="https://agentmods.dev/hooks/rafael-adcp/kraken/stop-failure"><img src="https://agentmods.dev/badge/hooks/rafael-adcp/kraken/stop-failure.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
StopFailure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
53% identical to SessionStart — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"StopFailure": [
{
"matcher": "rate_limit",
"hooks": [
{
"type": "command",
"command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/stop-failure-release.sh\""
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 13 lines scan A 43376f1c0e7b
StopFailure is a hook published in the GitHub repository rafael-adcp/kraken (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. It is 53% identical to SessionStart, differing in 8 lines, and is treated as a copy.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing handler.cjs via node. From Samuel0101010/wisp-orchestrator.
SessionStart
Runs when a session starts, executing session-registry-start.sh, parked-resume-check.sh and wip-check.sh via bash (3 commands). From Habitat-Thinking/ai-literacy-superpowers.
PreToolUse
Runs before the agent uses a tool for Write and Edit tool calls, executing markdownlint-check.sh via bash. From Habitat-Thinking/ai-literacy-superpowers.
PostToolUse
Runs after a tool call finishes, executing handler.cjs via node. From Samuel0101010/wisp-orchestrator.
SubagentStart
Runs when a subagent starts, executing relay-watch.js via node. From Teknesyum/Teknesyum-Base.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing inject-supervision.mjs via node. From ma-nucho-pro/supervisorLLM-plugin.